© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 25341
    Prev
    Next
    INDEX
    Explanations

    structure-activity relationship studies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     abon
    -0.07
     Staub
    -0.07
    tee
    -0.07
     maria
    -0.07
    æķĻèĤ²åİħ
    -0.07
    æ¯ıçıŃ
    -0.07
    æį¢æ°Ķ
    -0.07
    认è¯ģåķĨ家
    -0.07
    вла
    -0.07
    ạy
    -0.07
    POSITIVE LOGITS
     targeting
    0.09
     potency
    0.09
     pharm
    0.09
    aceutical
    0.09
     drug
    0.09
    æĪIJçĺ¾
    0.08
    æĪIJèį¯
    0.08
     pharmaceutical
    0.08
     Drug
    0.08
    ä¸Ģ代
    0.08
    Activations Density 0.377%

    No Known Activations